Title: Detection of vocal fold paralysis and oedema using time-domain features and Probabilistic Neural Network

Authors: M. Hariharan, M.P. Paulraj, Sazali Yaacob

Addresses: School of Mechatronic Engineering, Universiti Malaysia Perlis (UniMAP), Jejawi 02600, Perlis, Malaysia. ' School of Mechatronic Engineering, Universiti Malaysia Perlis (UniMAP), Jejawi 02600, Perlis, Malaysia. ' School of Mechatronic Engineering, Universiti Malaysia Perlis (UniMAP), Jejawi 02600, Perlis, Malaysia

Abstract: This paper proposes a feature extraction method based on time-domain energy variation for the detection of vocal fold pathology. In this work, two different vocal fold problems (vocal fold paralysis and edema) are taken for analysis and in either case, a two-class pattern recognition problem is investigated. The normal and pathological speech samples are used from Massachusetts Eye and Ear Infirmary database. Probabilistic Neural Network (PNN) is employed for the classification. The experimental results show that the proposed features give very promising classification accuracy of 90% and can be used to detect the vocal fold paralysis and edema clinically.

Keywords: vocal fold pathology; acoustic analysis; time-domain energy features; PNN; probabilistic neural networks; vocal fold paralysis; edema; feature extraction; speech signals; voice.

DOI: 10.1504/IJBET.2011.040452

International Journal of Biomedical Engineering and Technology, 2011 Vol.6 No.1, pp.46 - 57

Published online: 21 Jan 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article